© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12241
    Prev
    Next
    INDEX
    Explanations

    election statement

    np_acts-logits-general · gemini-2.5-flash-lite

    Explanation of neuron 4 behavior: the main thing this neuron does is find tokens that immediately follow numeric or measurement-like values (especially numbers with decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝓪
    1.06
    на
    1.05
    ни
    1.04
    oarece
    0.94
     nombreuses
    0.88
     secrétaire
    0.87
     необхід
    0.86
     τοῦ
    0.86
    일
    0.85
     încă
    0.84
    POSITIVE LOGITS
     elections
    0.75
     dined
    0.75
     one
    0.73
    ctors
    0.73
     psychology
    0.72
    扆
    0.72
    time
    0.71
     weighing
    0.71
    ेटिव
    0.70
     Muj
    0.70
    Activations Density 0.000%

    No Known Activations